Misaligned Over-The-Air Computation of Multi-Sensor Data with Wiener-Denoiser Network

TL;DR

This paper introduces a novel deep learning approach combining Wiener filtering and U-Net denoising to improve over-the-air computation accuracy in multi-sensor data aggregation despite synchronization and channel estimation issues.

Contribution

It formulates the misalignment problem as an image deblurring task and proposes a Wiener-Denoiser Network that outperforms traditional methods in over-the-air computation.

Findings

The proposed method effectively mitigates misalignment effects.

It achieves higher accuracy than traditional deblurring and denoising techniques.

The approach is robust to practical synchronization and channel estimation errors.

Abstract

In data driven deep learning, distributed sensing and joint computing bring heavy load for computing and communication. To face the challenge, over-the-air computation (OAC) has been proposed for multi-sensor data aggregation, which enables the server to receive a desired function of massive sensing data during communication. However, the strict synchronization and accurate channel estimation constraints in OAC are hard to be satisfied in practice, leading to time and channel-gain misalignment. The paper formulates the misalignment problem as a non-blind image deblurring problem. At the receiver side, we first use the Wiener filter to deblur, followed by a U-Net network designed for further denoising. Our method is capable to exploit the inherent correlations in the signal data via learning, thus outperforms traditional methods in term of accuracy. Our code is available at https://github.com/auto-Dog/MOAC_deep